[PATCH] D116375: [X86] Use bit test instructions to optimize some logic atomic operations

[Craig Topper via Phabricator via llvm-commits]

craig.topper added a comment.

This test fails

  %"struct.std::atomic" = type { %"struct.std::__atomic_base" }                    
  %"struct.std::__atomic_base" = type { i32 }                                      
                                                                                   
  @x = global %"struct.std::atomic" zeroinitializer, align 4                       
                                                                                   
  define i32 @_Z3fooii(i32 %0, i32 %1) {                                           
    %3 = atomicrmw or i32* getelementptr inbounds (%"struct.std::atomic", %"struct.std::atomic"* @x, i64 0, i32 0, i32 0), i32 8 seq_cst, align 4
    %4 = tail call i32 @llvm.ctlz.i32(i32 %0, i1 false)                            
    %5 = and i32 %3, 8                                                             
    %6 = icmp ne i32 %5, 0                                                         
    %7 = icmp ne i32 %1, 0                                                         
    %8 = select i1 %6, i1 %7, i1 false                                             
    br i1 %8, label %9, label %10                                                  
                                                                                   
  9:                                                ; preds = %2                   
    tail call void @_Z3bazi(i32 %4)                                                
    br label %10                                                                   
                                                                                   
  10:                                               ; preds = %9, %2               
    ret i32 %4                                                                     
  }                                                                                
                                                                                   
  declare i32 @llvm.ctlz.i32(i32, i1 immarg)                                       
                                                                                   
  declare void @_Z3bazi(i32)

CodeGenPrepare splits the basic block to despeculate the ctlz.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D116375/new/

https://reviews.llvm.org/D116375